claude-agent-sdk-typescript
Warn
Audited by Snyk on Feb 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md's "MCP Integration (External Servers)" shows the agent configured to call an external GitHub MCP server (e.g., using @modelcontextprotocol/server-github) to "List open issues in the repo", which clearly fetches user-generated, public third-party content that the agent reads and acts on.
Audit Metadata